R Notebook

library(dplyr)

Attaching package: <U+393C><U+3E31>dplyr<U+393C><U+3E32>

The following objects are masked from <U+393C><U+3E31>package:stats<U+393C><U+3E32>:

    filter, lag

The following objects are masked from <U+393C><U+3E31>package:base<U+393C><U+3E32>:

    intersect, setdiff, setequal, union

data <- read.csv("C:/Users/kzorina/Studing/MMDS/FutureOfWikipedia/data/df_all_with_timestamps.csv", encoding = "UTF-8")
data

cleaned_data <- data %>% 
  mutate(Ukr_time = as.POSIXct(uk_timestamp, format = "b'%Y%m%d%H%M%S'"),
         Eng_time = as.POSIXct(en_timestamp, format = "b'%Y%m%d%H%M%S'")) %>% 
  mutate(Time_to_translation = as.difftime(Eng_time-Ukr_time, units = "secs")) %>% 
  mutate(Time_to_translation_days = as.integer(as.numeric(Time_to_translation, units = "days"))) %>% 
  mutate(Time_to_translation_hours = as.integer(as.numeric(Time_to_translation, units = "hours"))) %>% 
  select(uk_id,uk_title, en_id, en_title, Ukr_time, Eng_time, Time_to_translation_hours, Time_to_translation_days)
cleaned_data

ukr_early_eng <- na.omit(cleaned_data[cleaned_data$Time_to_translation_hours > 0,])
ukr_early_eng

na_DF <- cleaned_data[is.na(cleaned_data$Time_to_translation_days),]
na_DF

library(pracma)
hist(ukr_early_eng$Time_to_translation_days, 
     breaks=linspace(min(ukr_early_eng$Time_to_translation_days)-0.5, max(ukr_early_eng$Time_to_translation_days)+0.5, n = 70),
     main = "Time before translation (days)",
     col = "#66A4A5",
     xlab = "Days from Ukr page creation to Eng page creation",
     ylab = "Amount of such pages")

linspace(min(ukr_early_eng$Time_to_translation_days)-0.5, max(ukr_early_eng$Time_to_translation_days)+0.5, n = 70)

Error in linspace(min(ukr_early_eng$Time_to_translation_days) - 0.5, max(ukr_early_eng$Time_to_translation_days) +  : 
  could not find function "linspace"

peak_data

library(ggplot2)
library(plotly)
g <- ggplot() +
  geom_point(data = peak_data, 
             aes(x = Ukr_time, 
                 y = Time_to_translation_days, 
                 text =      paste("time:", strftime(Ukr_time, format="%Y-%m-%d %H:%M:%S"), 
                                   "eng translation:",Eng_time
                                   #,"page title:",eval(parse(uk_title))
                                   )), col = "red", shape = 4,  size = 1)+
  labs(x = "Creation date of Ukr page", y = "Days from Ukr page creation to Eng page creation")

Ignoring unknown aesthetics: text

p = ggplotly(g);

We recommend that you use the dev version of ggplot2 with `ggplotly()`
Install it with: `devtools::install_github('hadley/ggplot2')`

p